MD ISTIAK AHAMMED
Research Assistant
Intelligent Construction Automation Center(ICA)
Robot & Smart System Engineering
Kyungpook National University
Daegu, South Korea
ADDRESS
20-3 Daehak-ro, Buk-gu, Daegu Metropolitan City (41567), South Korea
CV >>
Md. Istiak Ahammed was born in Pabna, Rajshahi, Bangladesh on 12 July. Currently, he is doing a masters in the Robot and Smart System Engineering Department at Kyungpook National University, South Korea. Along with this, he is working as a Graduate Research Assistant at Intelligent Construction Automation Center (ICA) where he is dedicated to developing intelligent systems for construction sites using machine learning and deep learning techniques. He also completed his undergraduate in Electrical & Electronic Engineering from Southeast University in 2019.
RESEARCH INTEREST
Artificial Intelligence, Autonomous Vehicles, Self-driving Cars, 3-D Vision and Recognition, Sensing & Perception, Sensing and Estimation, Computer Vision, Robotics, Aerial Robotics, Motion Planning, Simultaneous Localization and Mapping, Active Perception, Image and Signal Processing, Pattern Recognition, Machine Learning, Deep Learning, Intelligent Transportation Systems, Automation in Construction
EDUCATION
Kyungpook National University, Daegu, South Korea 2022 - 2024
M.Sc. in Robot and Smart System Engineering
Thesis: Acoustic-based Multitask Construction Equipment and Activity Recognition Using Customized ResNet-18
Advisor: Dr. Dong-Eun Lee
​
Southeast University, Dhaka, Bangladesh 2015 - 2019
B.Sc. in Electrical & Electronic Engineering
Thesis: Simulation Based Analysis of Permanent Magnet Synchronous Machines
Advisor: Abdullah Al Mahfazur Rahman
RESEARCH EXPERIENCE
GRADUATE RESEARCH
Acoustic-based Multitask Construction Equipment and Activity Recognition Using Customized ResNet-18
Status: Under Review
This work demonstrates to recognition of the multiple heavy equipment and their corresponding activities in the construction sites using sound they created based on the mel-spectrogram and Convolutional Neural Network (CNN). Specifically, herein I used a pre-trained ResNet-18 model including several audio signal augmentation techniques such as adding Gaussian noise, pitch shifting, phase shifting, normalizing, etc. The results of the study showed 99% accuracy for equipment classification and 98% accuracy for activities classification.
Location-Based Missing Wind Velocity Imputation Around the Buildings Using Deep Learning
Status: It is currently being processed for journal submission
This approach focuses to investigate the pattern of wind velocities and estimating the unmeasured values as a result of laser light shielding at the nearest large locations around the buildings. In order to estimate the missing wind values, we made use of three distinct ML models. These models were the generative adversarial imputation Network (GAIN), the multiple imputations by chained equations (MICE), and the neighbored distanced imputation (NDI). Results have evaluated by different evaluation metrics such as variance, standard deviation, MSE, and RMSE.
UNDERGRADUATE RESEARCH
Simulation-Based Analysis of Permanent Magnet Synchronous Machines
This research work demonstrates the simulation of field-oriented control of PMSM. The main reason for this is that, in field-oriented control, both torque and speed can be controlled independently by two currents responsible for torque and flux controlling separately. The whole system is simulated based on the mathematical model of PMSM and field-oriented control method with designed PI controllers.
UNDERGRADUATE PROJECT
Line Follower Restaurant Robot by Using Arduino
During the undergraduate program, a line follower robotic research, and project was carried out. It was also displayed at an electrical and electronic project fair conducted by the department of EEE at Southeast University in Dhaka, Bangladesh.
SKILLS
Operating System
-
​Windows
-
Linux
-
Ubuntu
Programming Languages
-
Python(Intermediate)
-
C++(Basic)
-
Julia(Basic)
-
Matlab (Basic)
Python Librarie
PyTorch, Keras, Pandas, NumPy, Matplotlib, Tensorflow, Audiomentation, OpenCV, Scikit-Learn, Scikit-Image
Deep Learning Algorithm
Convolutional Neural Networks (CNNs), Long Short Term Memory Networks (LSTMs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), Multilayer Perceptrons (MLPs), Autoencoders
Application Software
Anaconda(Fluent), Pycharm(Fluent), Visual Studio(Intermediate), MATLAB(Intermediate),Jupiter Notebook(Fluent), AutoCAD(Basic),Arduino(Basic), Google Collab(Fluent), Proteus(Basic), CoppeliaSim Edu(Basic), CARLA(Basic)
Python Framework
-
PyTorch (Intermediate)
-
Tensorflow (Intermediate)
Machine Learning Algorithm
Linear Regression, Logistic Regression, Decision Tree, Support Vector Machine (SVM), Naive Bayes algorithm, KNN algorithm, Random forest algorithm
AWARDS
1. KNU International Graduate Scholarship(KINGS)
Kyungpook National University, South Korea
2. Teaching Assistants (TA)
Kyungpook National University, South Korea
3. Academic Merit Scholarship
Southeast University, Bangladesh
4. Primary School Certificate (PSC) Scholarship
Directorate of Primary Education (DPE), Bangladesh